Thesis topic: Efficient Interaction through Information Maximization Context: Designing user interfaces is an iterative process. A designer creates an initial version based on their intuition and experience, then tests it with users and refines it based on feedback. This cycle is repeated until the interface is considered satisfactory. While effective, this…
Context and Objectives Governing is forecasting. This proverbial saying is relevant to many situations of engineering interest where decisions must be taken based on predictions or when devising a suitable sequence of actions to achieve some goal requires a good knowledge of the effect of these actions onto the system…
Funding: The project is funded for three years by the MIAI Cluster (Multidisciplinary Institute in Artificial Intelligence) Location: Grenoble Keywords: X-ray Dark-field Imaging, Small Angle X-ray Scattering, Computational X-rays, ImageReconstruction, Deep Learning Overview: This doctoral project aims to dramatically reduce the acquisition time and computational requirements of small-angle X-ray scattering…
Funding: The project is funded for three years by the MIAI Cluster (Multidisciplinary Institute in Artificial Intelligence) Location: Grenoble ou Lyon Keywords: Ghost Tomography, Computational X-rays, Image Reconstruction, Deep Learning. Overview: This doctoral project aims to develop a groundbreaking 3D imaging technique for non-destructive elemental analysis by merging the principles…
Compétences attendues : Le/la candidate recherché(e) sera issu(e) d’une formation en traitement du signal, mathématiques appliquées ou apprentissage automatique. Il/elle devra être intéressé(e) par les aspects théoriques et expérimentaux liés à l’application visée. Sujet de thèse : Dans le contexte du monitoring fœtal, le cardiotocogramme (CTG), basé sur une mesure…
Keywords Computer Vision, Photogrammetry, denes matching, multi view stereo, deep learning, multi-model Contexte Traditional 3D reconstruction methods based on stereo dense matching or Multi-View Stereo (MVS) reconstruction rely solely on photogrammetry and often fail in areas with low texture, specular surfaces, or complex geometries [6,8]. Meanwhile, LiDAR systems produce dense…
Une campagne de recrutement d’un doctorant informatique (IA / robotique) est ouverte à l’Ecole Navale au sein de l’équipe de recherche sur les drones à l’IRENav (EA 3634, Lanvéoc-Poulmic, https://www.ecole-navale.fr). Le sujet porte sur l’intelligence artificielle appliquée à l’appontage autonome de drones en environnement maritime complexe. Lieu : Institut de…
Cette thèse vise à concevoir une nouvelle génération de réseaux de neurones binarisés ou fortement quantifiés pour le traitement de données issues de caméras à événements sur plateformes embarquées. Contrairement aux caméras conventionnelles, les caméras événementielles produisent des flux asynchrones et parcimonieux décrivant les variations locales de luminance, offrant une…
Context PolInSAR (Polarimetric Interferometric SAR) combines polarimetry and radar interferometry for Earth observation [1]. This technique leverages the polarimetric sensitivity to scattering mechanisms and the interferometric sensitivity to the vertical structure of targets, enabling the estimation of forest height and biomass over large spatial areas [2, 3]. PolInSAR image processing…
Supervisors: A. Macario Barros · F.-M. Ngoule Mboula Laboratoire Instrumentation Intelligente, Distribuée et Embarquée (LIIDE) · CEA Start: October 2026 · Deadline: May 18, 2026 Automatic detection, 3D localization and classification of acoustic events (falls, alarms, gunshots) in uncontrolled environments remains an open problem. Existing approaches rely on microphone arrays…
